activity
20162023
most citedDynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

311 citations · 815 across the 62 of their papers we have counts for

collaborators
Showing 2021Show all

21 papers · 1 filter

cs.CL2021

Model Uncertainty-Aware Knowledge Amalgamation for Pre-Trained Language Models

Lei Li, Yankai Lin, Xuancheng Ren +4

As many fine-tuned pre-trained language models~(PLMs) with promising performance are generously released, investigating better ways to reuse these models is vital as it can greatly…

cs.CL2021★ 57 cited

On Transferability of Prompt Tuning for Natural Language Processing

Yusheng Su, Xiaozhi Wang, Yujia Qin +10

Prompt tuning (PT) is a promising parameter-efficient method to utilize extremely large pre-trained language models (PLMs), which can achieve comparable performance to full-paramet…

cs.CL2021★ 7 cited

Exploring Universal Intrinsic Task Subspace via Prompt Tuning

Yujia Qin, Xiaozhi Wang, Yusheng Su +10

Why can pre-trained language models (PLMs) learn universal representations and effectively adapt to broad NLP tasks differing a lot superficially? In this work, we empirically find…

cs.CL2021★ 1 cited

MoEfication: Transformer Feed-forward Layers are Mixtures of Experts

Zhengyan Zhang, Yankai Lin, Zhiyuan Liu +3

Recent work has shown that feed-forward networks (FFNs) in pre-trained Transformers are a key component, storing various linguistic and factual knowledge. However, the computationa…

cs.LG2021★ 1 cited

Feature Correlation Aggregation: on the Path to Better Graph Neural Networks

Jieming Zhou, Tong Zhang, Pengfei Fang +2

Prior to the introduction of Graph Neural Networks (GNNs), modeling and analyzing irregular data, particularly graphs, was thought to be the Achilles' heel of deep learning. The co…

cs.CV2021★ 29 cited

Reasoning Graph Networks for Kinship Verification: from Star-shaped to Hierarchical

Wanhua Li, Jiwen Lu, Abudukelimu Wuerkaixi +2

In this paper, we investigate the problem of facial kinship verification by learning hierarchical reasoning graph networks. Conventional methods usually focus on learning discrimin…